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. 9032
    Prev
    Next
    INDEX
    Explanations

    Music key signatures

    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
     radius
    -0.08
    iameter
    -0.08
     humaine
    -0.08
     intercourse
    -0.08
     television
    -0.08
     diameter
    -0.07
     heterogeneous
    -0.07
    (radius
    -0.07
    _APPRO
    -0.07
    radius
    -0.07
    POSITIVE LOGITS
     എണ്ണ
    0.08
    雪
    0.08
     snowfall
    0.08
     fewer
    0.08
    越来越
    0.08
     استاد
    0.07
    ifar
    0.07
     sombre
    0.07
    itso
    0.07
     SSE
    0.07
    Activations Density 0.003%

    No Known Activations