© 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. 11-RESID-POST-AA
    11. 91222
    Prev
    Next
    INDEX
    Explanations

    string manipulation

    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
     Ug
    -0.08
     compile
    -0.08
    _pen
    -0.08
    �
    -0.07
     assume
    -0.07
    _nf
    -0.07
    _##
    -0.07
    _live
    -0.07
    Live
    -0.07
    _ER
    -0.07
    POSITIVE LOGITS
    getline
    0.09
     whipping
    0.09
     Parsing
    0.09
    长度
    0.09
     getline
    0.08
    liked
    0.08
     चेहरे
    0.08
     fgets
    0.08
     Vom
    0.08
    Deque
    0.07
    Activations Density 0.004%

    No Known Activations