© 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. 91233
    Prev
    Next
    INDEX
    Explanations

    c

    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
    amay
    -0.09
    halts
    -0.09
    nader
    -0.08
    mute
    -0.08
    arians
    -0.08
     Naf
    -0.08
     calming
    -0.08
    arian
    -0.08
    tering
    -0.08
    Sessions
    -0.08
    POSITIVE LOGITS
     높
    0.09
    ，根据
    0.08
     calculated
    0.08
     вычис
    0.08
    ံ
    0.08
     اخ
    0.07
     계산
    0.07
     읽
    0.07
     sqrt
    0.07
     앱
    0.07
    Activations Density 0.006%

    No Known Activations