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. 42919
    Prev
    Next
    INDEX
    Explanations

    dilation/stretch

    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
     Polen
    -0.09
    Hue
    -0.09
     genet
    -0.08
     mulig
    -0.08
    озмож
    -0.08
     možnosti
    -0.08
    ennung
    -0.07
    advance
    -0.07
     təmin
    -0.07
     vlak
    -0.07
    POSITIVE LOGITS
    /cr
    0.08
    amic
    0.08
    alous
    0.08
     Anyway
    0.07
    Balanced
    0.07
     gu
    0.07
    _AD
    0.07
    .prec
    0.07
     refinement
    0.07
     cam
    0.07
    Activations Density 0.002%

    No Known Activations