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. 60481
    Prev
    Next
    INDEX
    Explanations

    infinite

    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
     afgest
    -0.09
     deduct
    -0.08
     ನಡೆಯ
    -0.08
     રચ
    -0.08
     Nus
    -0.08
     పాటు
    -0.08
     desfr
    -0.08
    _notification
    -0.08
    的钱
    -0.08
    Watching
    -0.08
    POSITIVE LOGITS
    itched
    0.07
     indicates
    0.07
    -m
    0.07
    /ext
    0.07
    ibong
    0.07
    .Initial
    0.07
     Essentially
    0.07
    ocal
    0.07
     essentially
    0.07
    oc
    0.07
    Activations Density 0.006%

    No Known Activations