Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 130479
    Prev
    Next
    INDEX
    Explanations

    -width

    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
     scat
    -0.08
    Payroll
    -0.08
     scouting
    -0.07
    tractor
    -0.07
     scatter
    -0.07
     Der
    -0.07
     Payroll
    -0.07
     scattering
    -0.07
    باط
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     estrict
    0.09
     strictly
    0.08
     menjaga
    0.08
     সীম
    0.08
    严格
    0.08
    /he
    0.08
    .strict
    0.08
    Constraints
    0.08
    STRICT
    0.08
     unforeseen
    0.08
    Activations Density 0.002%

    No Known Activations