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. 9123
    Prev
    Next
    INDEX
    Explanations

    copy/paste editing

    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
     శ
    -0.08
    �果
    -0.08
    umbre
    -0.08
     XL
    -0.08
     య
    -0.08
    為
    -0.07
     бул
    -0.07
     ég
    -0.07
    రిక
    -0.07
     unserem
    -0.07
    POSITIVE LOGITS
    imoto
    0.09
    MEM
    0.08
    winkel
    0.08
    odz
    0.07
    é
    0.07
    moire
    0.07
     ct
    0.07
     intelligence
    0.07
    Existing
    0.07
     chaud
    0.07
    Activations Density 0.001%

    No Known Activations