© 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. 30192
    Prev
    Next
    INDEX
    Explanations

    code

    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
     май
    -0.09
     nucleotide
    -0.09
     enzyme
    -0.08
    Ella
    -0.08
     cupid
    -0.08
     quantified
    -0.08
     Elasticsearch
    -0.08
     decoding
    -0.08
    әһ
    -0.08
     enzymes
    -0.08
    POSITIVE LOGITS
     fullscreen
    0.14
     HWND
    0.13
    fullscreen
    0.12
     UIWindow
    0.12
    (HWND
    0.11
     scrollbar
    0.11
    Fullscreen
    0.11
     hwnd
    0.10
    (hwnd
    0.10
    _FULLSCREEN
    0.10
    Activations Density 0.010%

    No Known Activations