© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129521
    Prev
    Next
    INDEX
    Explanations

    Area calculations

    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
     creen
    -0.09
     Hola
    -0.08
    _yes
    -0.08
     spinal
    -0.08
     ayer
    -0.08
     vino
    -0.07
    Hola
    -0.07
     hypnosis
    -0.07
     arquitect
    -0.07
    _axi
    -0.07
    POSITIVE LOGITS
    Magnitude
    0.10
     magnitude
    0.10
     paralle
    0.09
    orbit
    0.08
    .Vector
    0.08
    ATURE
    0.08
    ature
    0.08
    Folder
    0.08
     biv
    0.08
     orbit
    0.08
    Activations Density 0.017%

    No Known Activations