© 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. 11-RESID-POST-AA
    11. 95199
    Prev
    Next
    INDEX
    Explanations

    Outlines with numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rok
    -0.08
    ighted
    -0.08
    ünstler
    -0.08
    ov
    -0.07
    itek
    -0.07
     arreg
    -0.07
    ajak
    -0.07
     Sakura
    -0.07
     Penn
    -0.07
    Digit
    -0.07
    POSITIVE LOGITS
    iis
    0.08
     terapia
    0.08
     Falling
    0.08
     crema
    0.07
    াঞ্চ
    0.07
     fundada
    0.07
     Blank
    0.07
    /ou
    0.07
     terapi
    0.07
     payroll
    0.07
    Activations Density 0.038%

    No Known Activations