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. 30016
    Prev
    Next
    INDEX
    Explanations

    engine specifications

    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
     Directory
    -0.10
    Directory
    -0.08
    .Directory
    -0.08
    	Schema
    -0.08
    'a
    -0.08
    ింప
    -0.08
    -directory
    -0.08
    ുക്ക
    -0.08
    .bool
    -0.07
    _html
    -0.07
    POSITIVE LOGITS
     torque
    0.14
     rpm
    0.13
     Torque
    0.13
    Torque
    0.13
     gearbox
    0.12
     RPM
    0.11
     horsepower
    0.11
     locomotive
    0.11
     cyclist
    0.11
     pedals
    0.11
    Activations Density 0.014%

    No Known Activations