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. 15-RESID-POST-AA
    6. 19058
    Prev
    Next
    INDEX
    Explanations

    /

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     verification
    -0.08
     conquista
    -0.07
    Boss
    -0.07
    _GET
    -0.07
    (opts
    -0.07
    -ब
    -0.07
    edido
    -0.07
    pecified
    -0.07
     unless
    -0.07
    -b
    -0.07
    POSITIVE LOGITS
    alles
    0.09
     Wohnungen
    0.09
    orithms
    0.09
    wohnungen
    0.09
     woningen
    0.09
    ält
    0.08
     Landwirtschaft
    0.08
     viviendas
    0.08
     որոնք
    0.08
     Wann
    0.08
    Activations Density 0.017%

    No Known Activations