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. 53177
    Prev
    Next
    INDEX
    Explanations

    period

    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
     ঘটে
    -0.09
     PATH
    -0.08
     xảy
    -0.08
    PATH
    -0.08
     possibilidade
    -0.08
    _vue
    -0.07
    abilia
    -0.07
     PDO
    -0.07
     teoria
    -0.07
     നടന്ന
    -0.07
    POSITIVE LOGITS
     catchy
    0.09
    heavy
    0.09
     vintage
    0.08
     beve
    0.08
     hefty
    0.08
     deportivas
    0.08
     respiratory
    0.08
    icking
    0.08
     reputable
    0.08
     dul
    0.08
    Activations Density 0.008%

    No Known Activations