© 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. 8031
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    资金
    -0.08
     Ban
    -0.08
     مالي
    -0.07
     blind
    -0.07
     Camer
    -0.07
    ional
    -0.07
     Fridays
    -0.07
     confes
    -0.07
     مالی
    -0.07
    ್ತ
    -0.07
    POSITIVE LOGITS
     usability
    0.09
     tå
    0.08
     borderline
    0.08
     durability
    0.08
     exactement
    0.07
     diskr
    0.07
     genau
    0.07
    0.07
    ⇒
    0.07
     제외
    0.07
    Activations Density 0.040%
    No Known Activations