© 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. 1427
    Prev
    Next
    INDEX
    Explanations

    dd

    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
     degraded
    -0.08
     werde
    -0.07
    emde
    -0.07
     Roll
    -0.07
    acă
    -0.07
    ceb
    -0.07
    ocl
    -0.07
    asz
    -0.07
    mit
    -0.07
    rnd
    -0.07
    POSITIVE LOGITS
    改
    0.09
     विध
    0.08
     pará
    0.07
    击
    0.07
     Bam
    0.07
     imposs
    0.07
     �
    0.07
     माहित
    0.07
    相談
    0.07
     spear
    0.07
    Activations Density 0.001%

    No Known Activations