© 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. 3-RESID-POST-AA
    11. 12722
    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_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     huge
    -0.10
     сен
    -0.09
     awake
    -0.08
    Ont
    -0.08
     ener
    -0.08
    Subjects
    -0.07
     BLO
    -0.07
    Huge
    -0.07
     worldwide
    -0.07
    -sav
    -0.07
    POSITIVE LOGITS
     Jem
    0.08
     Ca
    0.08
     Kirst
    0.08
     Pathfinder
    0.07
    ̂
    0.07
     Caj
    0.07
     Sachs
    0.07
    �
    0.07
    ´t
    0.07
    括
    0.07
    Activations Density 0.002%

    No Known Activations