© 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. 19-RESID-POST-AA
    11. 102699
    Prev
    Next
    INDEX
    Explanations

    CSS styling

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     an
    -0.09
     some
    -0.08
    осн
    -0.08
    даем
    -0.07
     example
    -0.07
     endl
    -0.07
     a
    -0.07
    л
    -0.07
    some
    -0.07
     '
    -0.07
    POSITIVE LOGITS
    ophageal
    0.09
    avicon
    0.09
    .Circle
    0.09
    -format
    0.09
    ÁRIO
    0.09
    -Go
    0.09
    _RGBA
    0.09
     Making
    0.09
    _GUI
    0.08
    .Recycler
    0.08
    Activations Density 0.000%

    No Known Activations