© 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. 6213
    Prev
    Next
    INDEX
    Explanations

    stone carvings

    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
     parach
    -0.10
     fios
    -0.09
     coton
    -0.09
     hoses
    -0.09
     executivo
    -0.09
     électriques
    -0.09
     gasoline
    -0.09
     handbags
    -0.09
     couture
    -0.09
     Zucker
    -0.09
    POSITIVE LOGITS
     carv
    0.18
     stone
    0.17
     stones
    0.16
     limestone
    0.16
     sandstone
    0.16
    石
    0.15
     האבן
    0.15
     الحجر
    0.15
     moss
    0.15
     inscriptions
    0.15
    Activations Density 0.059%

    No Known Activations