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. 90027
    Prev
    Next
    INDEX
    Explanations

    .add

    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
     artifacts
    -0.08
     myths
    -0.08
    .mysql
    -0.08
     patents
    -0.08
    �
    -0.08
    .protocol
    -0.08
     skins
    -0.08
     prototypes
    -0.08
    appings
    -0.08
     Cine
    -0.07
    POSITIVE LOGITS
    Г
    0.09
    GRESS
    0.08
    П
    0.08
     госп
    0.08
    (single
    0.08
    (field
    0.08
     ем
    0.07
     consisted
    0.07
    Tank
    0.07
     Г
    0.07
    Activations Density 0.000%

    No Known Activations