© 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. 68077
    Prev
    Next
    INDEX
    Explanations

    Direct quotes/language use

    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
     kas
    -0.09
     dmg
    -0.09
    THOOK
    -0.08
     administrator
    -0.08
    ETS
    -0.08
     ETS
    -0.08
     ske
    -0.08
     AMS
    -0.08
     tis
    -0.08
    રો
    -0.07
    POSITIVE LOGITS
     somehow
    0.08
     indirectly
    0.08
     erwähnt
    0.08
    hatikan
    0.07
     refers
    0.07
    _word
    0.07
    ியாக
    0.07
     mencionado
    0.07
     vague
    0.07
     focuses
    0.07
    Activations Density 0.074%

    No Known Activations