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. 65880
    Prev
    Next
    INDEX
    Explanations

    can

    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
     aparentemente
    -0.09
    ???
    -0.08
    :'+
    -0.08
    Occupied
    -0.08
    却
    -0.08
     ???
    -0.08
    自治
    -0.08
     ";↵↵
    -0.07
    )#
    -0.07
     oner
    -0.07
    POSITIVE LOGITS
     structured
    0.09
     mezcl
    0.09
     inoltre
    0.09
     sentences
    0.08
     antimicrobial
    0.08
     weaving
    0.08
     Additionally
    0.08
     Scandin
    0.08
     Scandinavian
    0.08
     Provide
    0.08
    Activations Density 0.080%

    No Known Activations