Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 58683
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
     Mini
    -0.07
    ígeno
    -0.07
     ;↵
    -0.07
    Resumo
    -0.07
    orgh
    -0.07
    Β
    -0.07
    aco
    -0.07
     ở
    -0.07
     recrut
    -0.07
    ||||
    -0.07
    POSITIVE LOGITS
     போது
    0.08
    iffen
    0.07
    _UNIT
    0.07
     ftp
    0.07
     Preference
    0.07
    -film
    0.07
    _gallery
    0.07
    тын
    0.07
    von
    0.07
     CURLOPT
    0.07
    Activations Density 0.004%

    No Known Activations