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. 76298
    Prev
    Next
    INDEX
    Explanations

    tracks and following Method: 2, because the texts relate to adventure or tracks

    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
    _validate
    -0.08
    <boost
    -0.08
    ണമെന്ന്
    -0.08
    <IC
    -0.08
    ประช
    -0.07
    -0.07
    ాణ
    -0.07
    .validate
    -0.07
    <string
    -0.07
    ணம்
    -0.07
    POSITIVE LOGITS
     footprints
    0.17
     footprint
    0.14
    迹
    0.13
     footsteps
    0.13
     trails
    0.12
    �
    0.12
    踪
    0.12
     signatures
    0.12
     trail
    0.11
     traces
    0.11
    Activations Density 0.063%

    No Known Activations