© 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. 94873
    Prev
    Next
    INDEX
    Explanations

    Atomic weights

    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
    Divide
    -0.09
     масштаб
    -0.09
    ünd
    -0.08
     विभ
    -0.08
     Divide
    -0.08
     продвиж
    -0.08
     divide
    -0.07
    -0.07
     divis
    -0.07
     dividido
    -0.07
    POSITIVE LOGITS
     ions
    0.11
     atoms
    0.10
     kcal
    0.10
     chromatography
    0.10
     laboratorio
    0.09
     reagent
    0.09
    /mol
    0.09
     nuclei
    0.09
     adsorption
    0.09
     laboratory
    0.09
    Activations Density 0.008%
    No Known Activations