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. 112490
    Prev
    Next
    INDEX
    Explanations

    chess

    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
    pees
    -0.08
     Gip
    -0.08
    _diag
    -0.08
    oco
    -0.07
     replacement
    -0.07
     fragment
    -0.07
    post
    -0.07
    עה
    -0.07
    ösen
    -0.07
    -free
    -0.07
    POSITIVE LOGITS
     alphabetical
    0.09
     Letter
    0.09
     alfabet
    0.09
    Letter
    0.09
     letter
    0.08
     Technical
    0.08
     Alphabet
    0.08
    Technical
    0.08
     numbering
    0.08
    .MOD
    0.08
    Activations Density 0.005%

    No Known Activations