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. 67899
    Prev
    Next
    INDEX
    Explanations

    trauma

    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
     cadence
    -0.08
     rib
    -0.08
    mir
    -0.08
    grö
    -0.08
    surf
    -0.08
     rebates
    -0.07
    .download
    -0.07
     rebate
    -0.07
    _TRANSACTION
    -0.07
    Uv
    -0.07
    POSITIVE LOGITS
     Blank
    0.08
    युक्त
    0.07
     �
    0.07
     �
    0.07
     준
    0.07
     Holocaust
    0.07
     anteced
    0.07
    310
    0.07
     dull
    0.07
    歲
    0.07
    Activations Density 0.004%

    No Known Activations