© 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. 44833
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs

    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
     skat
    -0.09
     Azerbaijan
    -0.08
     nob
    -0.08
     enigmatic
    -0.08
     mundane
    -0.08
     somewhere
    -0.08
     ske
    -0.08
     Tribe
    -0.08
     reunion
    -0.07
     Airbus
    -0.07
    POSITIVE LOGITS
     sufficiently
    0.09
     δ
    0.08
    ittens
    0.08
    .radius
    0.08
    .small
    0.08
    Ɛ
    0.08
    (||
    0.08
    _delta
    0.08
     shrinking
    0.08
    _radius
    0.08
    Activations Density 0.009%

    No Known Activations