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. 12443
    Prev
    Next
    INDEX
    Explanations

    Mathematical formulas

    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
    וו
    -0.08
     aziende
    -0.08
    裙
    -0.08
     copying
    -0.07
     bleeding
    -0.07
     purchasing
    -0.07
    levant
    -0.07
     workflows
    -0.07
     lined
    -0.07
     mound
    -0.07
    POSITIVE LOGITS
     radians
    0.09
     cosine
    0.09
     Hubert
    0.08
     Carlson
    0.08
     Angle
    0.07
     Nijmegen
    0.07
    inus
    0.07
     Vin
    0.07
     Parque
    0.07
    IMATION
    0.07
    Activations Density 0.062%

    No Known Activations