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. 15-RESID-POST-AA
    6. 19418
    Prev
    Next
    INDEX
    Explanations

    Z, 1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Animal
    -0.08
     일부
    -0.07
     Futebol
    -0.07
     contradiction
    -0.07
     તેવી
    -0.07
     contradictory
    -0.07
     Playlist
    -0.07
     ఉప
    -0.07
     routed
    -0.07
     treball
    -0.07
    POSITIVE LOGITS
    _coef
    0.09
    _coeff
    0.09
    _formula
    0.09
     মর
    0.08
     coefficients
    0.08
    kab
    0.08
    vn
    0.08
     coefficient
    0.08
    etan
    0.08
     exprim
    0.08
    Activations Density 0.002%

    No Known Activations