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. 67299
    Prev
    Next
    INDEX
    Explanations

    1

    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
     Las
    -0.08
    each
    -0.08
     Paras
    -0.07
     offered
    -0.07
    การ
    -0.07
     सुविध
    -0.07
     Outstanding
    -0.07
     تق
    -0.07
     каж
    -0.07
     Exc
    -0.07
    POSITIVE LOGITS
    _DISABLE
    0.09
     禁
    0.08
    avoie
    0.08
    纪律
    0.08
    Barn
    0.08
     nasty
    0.07
    BAN
    0.07
     vermeiden
    0.07
    _RADIUS
    0.07
    奸
    0.07
    Activations Density 0.000%

    No Known Activations