© 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. 6251
    Prev
    Next
    INDEX
    Explanations

    A

    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
    入住
    -0.08
     srand
    -0.08
    ket
    -0.08
    гара
    -0.08
    umaan
    -0.07
    	arr
    -0.07
    ่านั้น
    -0.07
     الطفل
    -0.07
    Про
    -0.07
     arr
    -0.07
    POSITIVE LOGITS
    linear
    0.08
    /U
    0.08
     esclarecer
    0.08
     trocken
    0.07
     lore
    0.07
     esclare
    0.07
     Lightning
    0.07
    .linear
    0.07
     linear
    0.07
    Lightning
    0.07
    Activations Density 0.000%

    No Known Activations