© 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. 3-RESID-POST-AA
    11. 2683
    Prev
    Next
    INDEX
    Explanations

    Image

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oval
    -0.08
    CEA
    -0.08
    CHA
    -0.08
     Betreuung
    -0.08
    晋
    -0.08
     الول
    -0.08
     Enlarg
    -0.08
    Growth
    -0.08
     Enlargement
    -0.07
    АЛ
    -0.07
    POSITIVE LOGITS
    ciąż
    0.08
    .clear
    0.08
     wifi
    0.08
    ッ
    0.07
    över
    0.07
     SQL
    0.07
     தொக
    0.07
    fp
    0.07
    必
    0.07
    icarbon
    0.07
    Activations Density 0.000%

    No Known Activations