© 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. 47227
    Prev
    Next
    INDEX
    Explanations

    bleed

    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
     Pla
    -0.09
    ภ
    -0.08
    .deep
    -0.08
     Engel
    -0.08
    نف
    -0.07
    iliz
    -0.07
     drastic
    -0.07
    obar
    -0.07
    �
    -0.07
    梯
    -0.07
    POSITIVE LOGITS
    Into
    0.10
     into
    0.10
    _into
    0.09
    ออก
    0.09
     leaking
    0.08
     Fever
    0.08
    Bos
    0.08
     Into
    0.08
     Yar
    0.08
     gums
    0.07
    Activations Density 0.003%

    No Known Activations