© 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. 68098
    Prev
    Next
    INDEX
    Explanations

    remainder

    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
     pruž
    -0.09
     lighting
    -0.09
    ancies
    -0.08
     Wallet
    -0.08
     gifting
    -0.07
     shortlisted
    -0.07
     pricing
    -0.07
     gond
    -0.07
     vendors
    -0.07
    quettes
    -0.07
    POSITIVE LOGITS
    Typically
    0.09
    Supp
    0.09
    isierte
    0.09
    Castle
    0.08
    Situated
    0.08
    _Output
    0.08
    (Big
    0.08
     decree
    0.08
    <Self
    0.07
    (min
    0.07
    Activations Density 0.015%

    No Known Activations