© 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. 65448
    Prev
    Next
    INDEX
    Explanations

    e

    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
     Jedi
    -0.08
     MC
    -0.07
    �
    -0.07
     pul
    -0.07
    MC
    -0.07
     vigilant
    -0.07
     celebrity
    -0.07
     obedient
    -0.07
    овыми
    -0.07
    mc
    -0.07
    POSITIVE LOGITS
    isite
    0.09
     LOCATION
    0.08
    ROR
    0.08
    -location
    0.08
    gage
    0.08
    .Field
    0.08
    location
    0.07
    rico
    0.07
     আক্রান্ত
    0.07
    rei
    0.07
    Activations Density 0.001%

    No Known Activations