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. 24182
    Prev
    Next
    INDEX
    Explanations

    buffer

    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
     pert
    -0.09
     stabil
    -0.08
     stabilize
    -0.08
     perturb
    -0.07
    adi
    -0.07
    স্থিত
    -0.07
     clos
    -0.07
     fly
    -0.07
     heats
    -0.07
    pert
    -0.07
    POSITIVE LOGITS
     Them
    0.09
     Toshiba
    0.08
    ڙ
    0.08
    ブル
    0.08
    дений
    0.08
     Approved
    0.08
     bored
    0.08
    �რ
    0.08
    łącz
    0.08
    ambique
    0.07
    Activations Density 0.001%

    No Known Activations