© 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. 756
    Prev
    Next
    INDEX
    Explanations

    return token

    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
     controll
    -0.09
     giovani
    -0.08
     crec
    -0.08
    (Parameter
    -0.08
     mesi
    -0.08
     sobe
    -0.08
     fabri
    -0.08
     roku
    -0.07
     mesos
    -0.07
     bicic
    -0.07
    POSITIVE LOGITS
     Verdict
    0.08
    <|message|>
    0.07
     glad
    0.07
    Sure
    0.07
    /ioutil
    0.07
    арай
    0.07
    atrième
    0.07
     concludes
    0.07
    <|return|>
    0.07
    ↵↵↵↵↵
    0.07
    Activations Density 0.016%

    No Known Activations