© 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. 97799
    Prev
    Next
    INDEX
    Explanations

    Formulas

    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
    Let's
    -0.11
    #+#+
    -0.10
    Actually
    -0.10
    Anyway
    -0.10
    Exactly
    -0.09
    Which
    -0.09
     :(↵↵
    -0.09
    We'll
    -0.09
    7
    -0.09
    Candidate
    -0.09
    POSITIVE LOGITS
    /V
    0.17
    _eff
    0.15
    /T
    0.15
    ,V
    0.14
    ,T
    0.14
    /v
    0.14
    /R
    0.14
    /N
    0.13
    _tot
    0.13
    ,v
    0.13
    Activations Density 0.082%

    No Known Activations