© 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. 24685
    Prev
    Next
    INDEX
    Explanations

    w

    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
     galvan
    -0.08
    صح
    -0.08
     neu
    -0.07
     Gir
    -0.07
    �
    -0.07
    DAQ
    -0.07
     Ion
    -0.07
     ions
    -0.07
    numer
    -0.07
    Blu
    -0.07
    POSITIVE LOGITS
    avelength
    0.10
    elfare
    0.08
    inners
    0.08
    elcome
    0.08
    ritable
    0.07
     Data
    0.07
    ী
    0.07
    ednes
    0.07
    стреч
    0.07
     labyrinth
    0.07
    Activations Density 0.318%

    No Known Activations