© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2749
    Prev
    Next
    INDEX
    Explanations

    over

    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
     booming
    -0.08
     Salam
    -0.08
    Sant
    -0.08
    bout
    -0.07
    Hostname
    -0.07
     gente
    -0.07
     Must
    -0.07
     reform
    -0.07
     Sabb
    -0.07
     Or
    -0.07
    POSITIVE LOGITS
     farther
    0.08
    endl
    0.08
    ーク
    0.07
    कारी
    0.07
     considere
    0.07
     tin
    0.07
     considered
    0.07
     uh
    0.07
    奇
    0.07
     sint
    0.07
    Activations Density 0.007%

    No Known Activations