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

    Neuronpedia

    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. 48835
    Prev
    Next
    INDEX
    Explanations

    foreign language snippets

    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
    erio
    -0.08
     rubric
    -0.08
     bati
    -0.08
     RBC
    -0.08
    302
    -0.07
    изи
    -0.07
     penso
    -0.07
     φορ
    -0.07
     izgub
    -0.07
     kriter
    -0.07
    POSITIVE LOGITS
    ával
    0.20
    ústr
    0.19
    úch
    0.17
    áme
    0.17
    égal
    0.17
    áll
    0.17
    ít
    0.17
    áj
    0.16
    ú
    0.16
     তোম
    0.16
    Activations Density 0.007%

    No Known Activations