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. 129820
    Prev
    Next
    INDEX
    Explanations

    Scheduling and coordination

    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
    Walls
    -0.07
     Walls
    -0.07
    atrib
    -0.07
     virtues
    -0.07
     walls
    -0.07
    .az
    -0.07
     surfaces
    -0.07
    relative
    -0.07
    orama
    -0.07
    lim
    -0.07
    POSITIVE LOGITS
     usos
    0.10
    用途
    0.09
     coexist
    0.09
     Bedürfnisse
    0.09
     চল
    0.08
     ajili
    0.08
     occupants
    0.08
     faaliyet
    0.08
    하면서
    0.08
     ನಡೆಯ
    0.08
    Activations Density 0.108%

    No Known Activations