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. 23392
    Prev
    Next
    INDEX
    Explanations

    location descriptions

    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
     नम
    -0.09
     noble
    -0.08
    -required
    -0.08
    ,sizeof
    -0.08
     exigences
    -0.07
    _stdio
    -0.07
     учет
    -0.07
     obligatory
    -0.07
    finding
    -0.07
     required
    -0.07
    POSITIVE LOGITS
    ועים
    0.08
    тостан
    0.08
    ⁣
    0.08
    南
    0.08
     Kit
    0.08
     Quil
    0.08
     mixes
    0.08
    臀
    0.08
     clips
    0.08
    北
    0.07
    Activations Density 0.077%

    No Known Activations