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. 12032
    Prev
    Next
    INDEX
    Explanations

    partial fractions

    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
    estro
    -0.08
    推动
    -0.08
     enterprises
    -0.08
    ery
    -0.07
     tri
    -0.07
     జర
    -0.07
     Joy
    -0.07
    Fuente
    -0.07
     લગભગ
    -0.07
    entre
    -0.07
    POSITIVE LOGITS
    Decay
    0.09
    _decay
    0.08
     residues
    0.08
    ADED
    0.08
    _FINAL
    0.08
    Intercept
    0.07
    _OTHER
    0.07
     verschiedenen
    0.07
     bereit
    0.07
     länger
    0.07
    Activations Density 0.009%

    No Known Activations