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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47195
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     confess
    -0.08
     tinct
    -0.08
     proverbial
    -0.07
    ,E
    -0.07
     мысл
    -0.07
     elic
    -0.07
    Via
    -0.07
    tit
    -0.07
     aired
    -0.07
     посредством
    -0.07
    POSITIVE LOGITS
     offset
    0.12
    offset
    0.12
    _offset
    0.11
    .offset
    0.11
    (offset
    0.10
    _OFFSET
    0.10
    CGFloat
    0.10
     clamp
    0.10
     Offset
    0.10
     Clamp
    0.10
    Activations Density 0.013%

    No Known Activations