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. 12410
    Prev
    Next
    INDEX
    Explanations

    equals

    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
    ði
    -0.07
    ুকে
    -0.07
    edding
    -0.07
    财经
    -0.07
    du
    -0.07
    Newton
    -0.07
    司法
    -0.07
     Police
    -0.07
    .search
    -0.07
    书记
    -0.07
    POSITIVE LOGITS
     helemaal
    0.08
     Apert
    0.08
    _Asp
    0.08
     porch
    0.08
     foc
    0.08
    .Session
    0.07
    	Session
    0.07
     ким
    0.07
     combines
    0.07
     Andaluc
    0.07
    Activations Density 0.010%

    No Known Activations