© 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. 2570
    Prev
    Next
    INDEX
    Explanations

    search

    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
     Hap
    -0.09
     mol
    -0.09
     hap
    -0.08
     oblige
    -0.08
     নগ
    -0.08
    疾
    -0.08
    IVER
    -0.08
     বিচ
    -0.08
    going
    -0.08
     Dream
    -0.07
    POSITIVE LOGITS
    तम
    0.10
    તમ
    0.08
    imum
    0.08
    Magnitude
    0.08
     aggress
    0.08
    Price
    0.08
     knobs
    0.08
    preset
    0.08
    dial
    0.07
    .Minimum
    0.07
    Activations Density 0.029%

    No Known Activations