© 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. 12869
    Prev
    Next
    INDEX
    Explanations

    challenge

    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
     бъ
    -0.09
    ರ್ಣ
    -0.08
     mākou
    -0.08
     ಪ್ರಮುಖ
    -0.08
     ವ್ಯಾಪ
    -0.07
     Ira
    -0.07
     xoog
    -0.07
     evidently
    -0.07
     కీల
    -0.07
    导师
    -0.07
    POSITIVE LOGITS
    reas
    0.08
    γρα
    0.08
     Flamengo
    0.07
     réuss
    0.07
    gaard
    0.07
     rewriting
    0.07
    0.07
     možnosti
    0.07
     Fest
    0.07
    fest
    0.07
    Activations Density 0.000%
    No Known Activations