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. 102975
    Prev
    Next
    INDEX
    Explanations

    graph theory

    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
    ssa
    -0.08
     slim
    -0.08
     కొన్ని
    -0.07
     digit
    -0.07
     usual
    -0.07
    Digit
    -0.07
    toon
    -0.07
     submenu
    -0.07
     అద
    -0.07
     sah
    -0.07
    POSITIVE LOGITS
     bid
    0.12
     Bid
    0.11
    Bid
    0.11
    (direction
    0.10
    bid
    0.10
    .bid
    0.09
    (Direction
    0.09
    _bid
    0.09
     symmetric
    0.09
     symmetrical
    0.09
    Activations Density 0.038%

    No Known Activations