© 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. 5932
    Prev
    Next
    INDEX
    Explanations

    say "6"

    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
    цу
    -0.08
    品牌
    -0.08
    .brand
    -0.08
    alamu
    -0.08
    _part
    -0.08
    爸爸
    -0.07
    _brand
    -0.07
    #SBATCH
    -0.07
    ;;;
    -0.07
     pror
    -0.07
    POSITIVE LOGITS
     choose
    0.15
     Choose
    0.12
    choose
    0.12
    Choose
    0.12
     bin
    0.12
     Bin
    0.11
    bin
    0.11
    -bin
    0.11
     choisissez
    0.11
    (bin
    0.11
    Activations Density 0.047%

    No Known Activations