© 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. 2744
    Prev
    Next
    INDEX
    Explanations

    -ing

    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
    ibor
    -0.09
    -0.07
     పంప
    -0.07
    cknow
    -0.07
    og
    -0.07
     mist
    -0.07
    ्रे
    -0.07
     Gar
    -0.07
     fra
    -0.07
     vend
    -0.07
    POSITIVE LOGITS
     �
    0.08
     actor
    0.08
    وان
    0.08
     فع
    0.08
    actor
    0.07
     involucr
    0.07
    acin
    0.07
     تع
    0.07
     carn
    0.07
     feats
    0.07
    Activations Density 0.126%
    No Known Activations