© 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. 1376
    Prev
    Next
    INDEX
    Explanations

    attack

    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
     Verd
    -0.09
     Arnold
    -0.08
     someday
    -0.08
     Beauty
    -0.08
    �
    -0.07
     Андрей
    -0.07
     thì
    -0.07
    音乐
    -0.07
     awọ
    -0.07
     Leonard
    -0.07
    POSITIVE LOGITS
     invent
    0.09
    (j
    0.08
     manufact
    0.08
    Magazine
    0.08
    ɛ
    0.07
    INSERT
    0.07
     keras
    0.07
     mérite
    0.07
    hf
    0.07
    genomen
    0.07
    Activations Density 0.000%

    No Known Activations