Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 27739
    Prev
    Next
    INDEX
    Explanations

    code

    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
    leş
    -0.08
     البرلمان
    -0.08
    enswert
    -0.08
    大战
    -0.08
    lelse
    -0.08
    лөг
    -0.07
    ansen
    -0.07
    LING
    -0.07
     segur
    -0.07
    স্পত
    -0.07
    POSITIVE LOGITS
    igno
    0.08
     piston
    0.07
     aine
    0.07
     dys
    0.07
     Gesch
    0.07
    aje
    0.07
     ilo
    0.07
     Allison
    0.07
     Maz
    0.07
     Gio
    0.07
    Activations Density 0.001%

    No Known Activations