© 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. 78309
    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
    .lst
    -0.08
     obec
    -0.08
    264
    -0.08
    推动
    -0.07
     دفع
    -0.07
     بالم
    -0.07
    正规的
    -0.07
     '@
    -0.07
    Cpp
    -0.07
     окружа
    -0.07
    POSITIVE LOGITS
     Controller
    0.08
    Residual
    0.08
     jähr
    0.07
    monthly
    0.07
    LEFT
    0.07
     concorr
    0.07
     Preliminary
    0.07
    /ch
    0.07
     ents
    0.07
    _daily
    0.07
    Activations Density 0.000%

    No Known Activations