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. 58293
    Prev
    Next
    INDEX
    Explanations

    Multiple languages and code

    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
    hele
    -0.08
     لج
    -0.08
     Household
    -0.08
     karm
    -0.08
     پا
    -0.07
     предлага
    -0.07
     душе
    -0.07
     MART
    -0.07
     pann
    -0.07
     фан
    -0.07
    POSITIVE LOGITS
    ങ്ങളിലും
    0.08
     derby
    0.08
     OMIT
    0.07
     Segunda
    0.07
    _then
    0.07
     deterministic
    0.07
     emphasized
    0.07
    ത്തു
    0.07
    maybe
    0.07
    !=
    0.07
    Activations Density 0.001%

    No Known Activations