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. 59686
    Prev
    Next
    INDEX
    Explanations

    the

    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
     neoliberal
    -0.10
     корруп
    -0.09
    :bold
    -0.09
    條
    -0.09
     mali
    -0.08
    upos
    -0.08
     Mach
    -0.08
     neol
    -0.08
     topic
    -0.08
     peril
    -0.08
    POSITIVE LOGITS
    Resultados
    0.08
     ദിവസ
    0.08
     resulted
    0.08
    839
    0.08
    _RESULT
    0.08
     ejec
    0.08
    Resultado
    0.08
    Result
    0.08
    _attempt
    0.07
    .Result
    0.07
    Activations Density 0.007%

    No Known Activations