© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 5928
    Prev
    Next
    INDEX
    Explanations

    col

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    340
    -0.09
    341
    -0.09
    370
    -0.08
    .carousel
    -0.08
     corred
    -0.08
    309
    -0.08
     suit
    -0.08
    310
    -0.08
     incline
    -0.08
    Seal
    -0.08
    POSITIVE LOGITS
    ımıza
    0.09
    ിമ
    0.09
     PCM
    0.09
    िम
    0.08
    ಿಮ
    0.08
    imizin
    0.08
    BZ
    0.08
     JMS
    0.08
    PCM
    0.08
     अपने
    0.07
    Activations Density 0.003%

    No Known Activations