Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 102838
    Prev
    Next
    INDEX
    Explanations

    set

    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
     metabolites
    -0.08
     kä
    -0.08
     Stephan
    -0.07
     soldiers
    -0.07
    ény
    -0.07
    uhalten
    -0.07
     analyt
    -0.07
     fome
    -0.07
    Random
    -0.07
     soldats
    -0.07
    POSITIVE LOGITS
     setter
    0.13
     overwrite
    0.11
    .setter
    0.10
     변경
    0.10
     Setter
    0.10
     менять
    0.09
     setattr
    0.09
    変更
    0.09
     орг
    0.09
    setter
    0.09
    Activations Density 0.006%

    No Known Activations