© 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. 54875
    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
     হও
    -0.09
     bolet
    -0.09
    旧
    -0.08
     Abb
    -0.08
    Death
    -0.08
     olds
    -0.08
    dob
    -0.08
    قي
    -0.08
    death
    -0.08
     misleading
    -0.08
    POSITIVE LOGITS
     тщательно
    0.08
     Option
    0.08
     مراجعه
    0.07
     استعمال
    0.07
     counsel
    0.07
     utiliser
    0.07
    care
    0.07
    _EXTERNAL
    0.07
     использу
    0.07
     பயன்படுத்த
    0.07
    Activations Density 0.028%

    No Known Activations