© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44894
    Prev
    Next
    INDEX
    Explanations

    common words

    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
     Needs
    -0.09
    ptide
    -0.09
    seca
    -0.09
    shoe
    -0.09
     Bade
    -0.08
    sẹ
    -0.08
    _enter
    -0.08
    hnliche
    -0.08
    ardino
    -0.08
    ニ
    -0.08
    POSITIVE LOGITS
     anarch
    0.09
     ideological
    0.09
     darknet
    0.09
     propaganda
    0.09
     clandest
    0.08
     xrange
    0.08
     prolet
    0.08
    /login
    0.08
     privileged
    0.08
     illicit
    0.08
    Activations Density 0.034%

    No Known Activations