© 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. 1459
    Prev
    Next
    INDEX
    Explanations

    Walker

    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
    akin
    -0.08
    chrom
    -0.08
    pole
    -0.08
    Pole
    -0.08
     chrom
    -0.08
     lanç
    -0.07
     chromosomes
    -0.07
     pole
    -0.07
    (function
    -0.07
    -elles
    -0.07
    POSITIVE LOGITS
     Filled
    0.09
     gau
    0.08
     fonte
    0.08
     vaut
    0.08
     inh
    0.08
     sitzt
    0.08
     Cent
    0.07
     Duty
    0.07
     disadvantage
    0.07
     Grenze
    0.07
    Activations Density 0.001%

    No Known Activations