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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43315
    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
     paga
    -0.10
     prestamos
    -0.09
     …
    -0.08
     पास
    -0.08
     ….
    -0.08
    पास
    -0.08
    ….
    -0.08
     pagos
    -0.08
     pago
    -0.08
    ….↵↵
    -0.07
    POSITIVE LOGITS
    _fake
    0.08
     blik
    0.08
    tk
    0.08
    Begin
    0.08
     beeld
    0.08
    beeld
    0.08
    Fake
    0.08
    redir
    0.08
    ечение
    0.07
    _INSERT
    0.07
    Activations Density 0.000%

    No Known Activations