© 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. 78944
    Prev
    Next
    INDEX
    Explanations

    transversal

    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
    ianne
    -0.08
     bloodstream
    -0.08
     centrifugal
    -0.07
    -0.07
     Haust
    -0.07
     विश्व
    -0.07
     Fox
    -0.07
     fairly
    -0.07
    əcək
    -0.07
    .enemy
    -0.07
    POSITIVE LOGITS
     vence
    0.08
    uluk
    0.08
    ůže
    0.08
    @stop
    0.07
     oled
    0.07
     barbe
    0.07
    Compl
    0.07
     imam
    0.07
     leggen
    0.07
     vê
    0.07
    Activations Density 0.000%
    No Known Activations