© 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. 738
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    protected
    -0.08
    anske
    -0.08
    prote
    -0.07
     Edit
    -0.07
     bescherming
    -0.07
    ACTIVE
    -0.07
     aren't
    -0.07
     Edinburgh
    -0.07
    gig
    -0.07
    heri
    -0.07
    POSITIVE LOGITS
     />↵↵
    0.09
    />↵
    0.09
    />↵↵
    0.09
     Finn
    0.08
     подробно
    0.08
    Som
    0.08
     предпоч
    0.08
     Abraham
    0.08
     />↵
    0.08
     nimi
    0.07
    Activations Density 0.007%

    No Known Activations