© 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. 3-RESID-POST-AA
    11. 12732
    Prev
    Next
    INDEX
    Explanations

    peel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     �
    -0.08
     ઉત્ત
    -0.08
     MAT
    -0.07
     potencial
    -0.07
     indicando
    -0.07
     mw
    -0.07
     pym
    -0.07
     taim
    -0.07
     poter
    -0.07
     indicar
    -0.07
    POSITIVE LOGITS
     dermatitis
    0.09
    arl
    0.08
    掉
    0.08
    coat
    0.08
     প্রতিব
    0.08
    0.08
     Gilles
    0.07
     hous
    0.07
    -cycle
    0.07
    _unused
    0.07
    Activations Density 0.003%
    No Known Activations