© 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. 6279
    Prev
    Next
    INDEX
    Explanations

    plane

    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
    ynomials
    -0.10
     val
    -0.10
    ysize
    -0.08
    (val
    -0.08
    val
    -0.08
    _val
    -0.08
    rewrite
    -0.08
    tolower
    -0.08
    -val
    -0.08
    ivalent
    -0.08
    POSITIVE LOGITS
     Π
    0.20
     Gamma
    0.17
    Π
    0.17
     Γ
    0.16
     Pi
    0.16
     Sigma
    0.16
     π
    0.15
     γ
    0.15
     Σ
    0.14
     �
    0.14
    Activations Density 0.054%

    No Known Activations