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. 54255
    Prev
    Next
    INDEX
    Explanations

    gold

    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
     bouquet
    -0.08
    ərbaycan
    -0.08
    방
    -0.08
    ONENT
    -0.08
    ostí
    -0.08
    حيان
    -0.08
    少女
    -0.08
    450
    -0.08
     فتاة
    -0.08
     �
    -0.08
    POSITIVE LOGITS
     Logging
    0.07
     to
    0.07
    seed
    0.07
    natur
    0.07
     sharpen
    0.07
     do
    0.07
     semantics
    0.07
     Not
    0.07
     x
    0.07
     possibilities
    0.07
    Activations Density 0.000%

    No Known Activations