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. 53269
    Prev
    Next
    INDEX
    Explanations

    Parenthesis

    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
     kah
    -0.09
     ham
    -0.08
    -0.08
     breeze
    -0.07
     cement
    -0.07
     pf
    -0.07
     soaking
    -0.07
     Becky
    -0.07
     speaker
    -0.07
     benz
    -0.07
    POSITIVE LOGITS
    దర్శ
    0.09
     అనే
    0.09
    Это
    0.08
     Это
    0.08
    uwd
    0.08
     Dieser
    0.08
    聞
    0.08
    ជ
    0.07
     ซึ่ง
    0.07
    ។
    0.07
    Activations Density 0.148%

    No Known Activations