Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 53915
    Prev
    Next
    INDEX
    Explanations

    sculpt

    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
    بود
    -0.08
    lack
    -0.08
    ോദ
    -0.08
    τέρα
    -0.08
    ე
    -0.08
    ärken
    -0.08
    ক্রম
    -0.07
     Umb
    -0.07
     Macron
    -0.07
    xd
    -0.07
    POSITIVE LOGITS
     sculptures
    0.10
     sculpture
    0.09
     biodegradable
    0.09
     antis
    0.08
    作品
    0.08
     opere
    0.08
    型
    0.08
     escult
    0.08
    ात्मक
    0.08
     chimney
    0.07
    Activations Density 0.008%

    No Known Activations