© 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. 29680
    Prev
    Next
    INDEX
    Explanations

    Shell

    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
     advantage
    -0.08
    优势
    -0.08
     disadvantages
    -0.08
     hər
    -0.07
     ҳар
    -0.07
     সর্ব
    -0.07
     advantages
    -0.07
    _events
    -0.07
    -life
    -0.07
    _max
    -0.07
    POSITIVE LOGITS
     garment
    0.09
     Punto
    0.09
     tonne
    0.09
     administrativos
    0.08
     данный
    0.08
     Zoll
    0.07
    .VERSION
    0.07
     convocatoria
    0.07
     schaut
    0.07
     surgical
    0.07
    Activations Density 0.000%

    No Known Activations