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. 45039
    Prev
    Next
    INDEX
    Explanations

    software

    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
     mustard
    -0.08
     ref
    -0.08
    ref
    -0.07
     meisje
    -0.07
     prednisone
    -0.07
    stress
    -0.07
     maintenance
    -0.07
    orden
    -0.07
     costo
    -0.07
    _PROM
    -0.07
    POSITIVE LOGITS
     Microgaming
    0.10
     beliebtesten
    0.08
     renowned
    0.08
     glazed
    0.08
     Seam
    0.08
     Laura
    0.08
     Proven
    0.07
     внед
    0.07
     گھ
    0.07
    putable
    0.07
    Activations Density 0.014%

    No Known Activations