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. 111760
    Prev
    Next
    INDEX
    Explanations

    application settings/configuration

    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
     psic
    -0.08
    _WRAP
    -0.07
     departamentos
    -0.07
     void
    -0.07
     sten
    -0.07
     widget
    -0.07
     railing
    -0.07
     luc
    -0.07
     protr
    -0.07
     length
    -0.07
    POSITIVE LOGITS
    Overrides
    0.10
     Dateien
    0.09
     Overrides
    0.09
     ~/.
    0.09
     merges
    0.09
     overrides
    0.09
     ergän
    0.09
     aanvullende
    0.09
     individuelle
    0.09
     individuell
    0.09
    Activations Density 0.007%

    No Known Activations