© 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. 169
    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
     lacquer
    -0.09
     sinus
    -0.08
    날
    -0.08
    wag
    -0.08
     Yok
    -0.08
    undle
    -0.08
    EXP
    -0.08
    %b
    -0.07
    ihar
    -0.07
    .wav
    -0.07
    POSITIVE LOGITS
     membership
    0.12
     Membership
    0.11
     సభ్య
    0.11
    _members
    0.10
    Membership
    0.10
    成员
    0.09
    -members
    0.09
     memberships
    0.09
    membership
    0.09
    embership
    0.09
    Activations Density 0.006%

    No Known Activations