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. 29823
    Prev
    Next
    INDEX
    Explanations

    here

    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
     existentes
    -0.07
     bestaande
    -0.07
    umm
    -0.07
    -shop
    -0.07
     orphan
    -0.07
     Dam
    -0.07
    'altra
    -0.07
    .fields
    -0.07
     jubil
    -0.07
    fields
    -0.07
    POSITIVE LOGITS
    ️
    0.08
    િક
    0.08
     ton
    0.08
    location
    0.08
    �
    0.08
     אית
    0.08
    кти
    0.08
    ్స
    0.08
    �
    0.08
    ಿಕ
    0.08
    Activations Density 0.000%

    No Known Activations