© 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. 96969
    Prev
    Next
    INDEX
    Explanations

    physical appearance

    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
     संचालन
    -0.09
     بحران
    -0.09
     Operation
    -0.08
     récit
    -0.08
     sovere
    -0.08
     निर्देशन
    -0.08
    irio
    -0.08
    操作
    -0.08
     subsidie
    -0.07
     irrigation
    -0.07
    POSITIVE LOGITS
     wygl
    0.33
     aparência
    0.32
     apariencia
    0.31
     physique
    0.31
     physiques
    0.29
     uiterlijk
    0.27
     appearance
    0.27
    Appearance
    0.27
     Appearance
    0.26
    appearance
    0.25
    Activations Density 0.196%

    No Known Activations