© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49456
    Prev
    Next
    INDEX
    Explanations

    Diagrams and grid arrangements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "encoding
    -0.10
    ’ann
    -0.10
    "github
    -0.10
    _async
    -0.10
    "errors
    -0.10
     njalo
    -0.10
    @Injectable
    -0.10
    .kafka
    -0.10
     asynchronously
    -0.10
     asynchronous
    -0.09
    POSITIVE LOGITS
    □□□□
    0.22
    □□□□□□□□
    0.22
     █
    0.19
    □□□□□□□□□□□□□□□□
    0.18
     ____
    0.18
     ................
    0.18
     ______
    0.18
     ■
    0.18
     _____
    0.18
     __________________
    0.18
    Activations Density 0.039%

    No Known Activations