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. 55878
    Prev
    Next
    INDEX
    Explanations

    gas

    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
    ">\
    -0.08
     shoes
    -0.08
    iked
    -0.08
    NEY
    -0.08
    UEL
    -0.07
     wiring
    -0.07
    491
    -0.07
     PCS
    -0.07
     liegt
    -0.07
     lê
    -0.07
    POSITIVE LOGITS
    -floating
    0.08
    .preference
    0.08
     ورو
    0.08
    proto
    0.08
    SO
    0.07
     weich
    0.07
     sapien
    0.07
    Rank
    0.07
     phased
    0.07
    emper
    0.07
    Activations Density 0.001%

    No Known Activations