© 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. 12946
    Prev
    Next
    INDEX
    Explanations

    بما

    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
     oks
    -0.08
    nta
    -0.08
     patr
    -0.08
     dra
    -0.08
     sano
    -0.08
     pik
    -0.08
    ggy
    -0.08
    বান
    -0.07
     flok
    -0.07
     jumping
    -0.07
    POSITIVE LOGITS
     Stewart
    0.08
     elevada
    0.08
     Sous
    0.08
     Meal
    0.08
     Steuer
    0.07
     Impress
    0.07
     Stella
    0.07
     Elaine
    0.07
     mors
    0.07
     �
    0.07
    Activations Density 0.000%

    No Known Activations