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. 77485
    Prev
    Next
    INDEX
    Explanations

    Driver

    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
     Guillaume
    -0.08
     kaksi
    -0.07
     Umfeld
    -0.07
    	is
    -0.07
     စ
    -0.07
     suivante
    -0.07
     Atmosphäre
    -0.07
     atmosphere
    -0.07
     intéressante
    -0.07
     pren
    -0.07
    POSITIVE LOGITS
     commonly
    0.08
    flok
    0.08
     čas
    0.08
    .pin
    0.08
    ારમાં
    0.07
    орту
    0.07
    Widget
    0.07
    Expired
    0.07
    0.07
    .chrom
    0.07
    Activations Density 0.001%

    No Known Activations