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. 30505
    Prev
    Next
    INDEX
    Explanations

    zero

    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
    tir
    -0.09
     teor
    -0.08
    amoto
    -0.07
     Man
    -0.07
    oning
    -0.07
     physic
    -0.07
     star
    -0.07
     cos
    -0.07
     poet
    -0.07
     Star
    -0.07
    POSITIVE LOGITS
     cien
    0.08
     Shorts
    0.08
    创建
    0.08
     clasp
    0.08
     ঠিক
    0.08
    partials
    0.08
    践
    0.08
    �
    0.08
     dock
    0.08
     shortlisted
    0.07
    Activations Density 0.001%

    No Known Activations