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. 119320
    Prev
    Next
    INDEX
    Explanations

    labor

    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
     réputation
    -0.09
    provider
    -0.08
    .until
    -0.08
     ספק
    -0.08
    iban
    -0.08
    μερ
    -0.07
     shading
    -0.07
    __('
    -0.07
    vor
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     childbirth
    0.10
    essing
    0.09
     climax
    0.08
     IVF
    0.08
    ежать
    0.08
     babies
    0.08
    施設
    0.08
     varieties
    0.08
     christ
    0.08
     instincts
    0.08
    Activations Density 0.013%

    No Known Activations