© 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. 23-RESID-POST-AA
    11. 48600
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -news
    -0.09
    -pane
    -0.08
    -lines
    -0.08
     invers
    -0.08
    opio
    -0.08
    setting
    -0.08
     combos
    -0.08
    orol
    -0.08
    closures
    -0.08
    -Free
    -0.08
    POSITIVE LOGITS
     multiple
    0.21
    multiple
    0.15
    _multiple
    0.14
     Multiple
    0.13
    Multiple
    0.12
     múltiples
    0.12
    多个
    0.12
     meerdere
    0.12
     member
    0.11
     عدة
    0.11
    Activations Density 0.049%

    No Known Activations