© 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. 68180
    Prev
    Next
    INDEX
    Explanations

    severe

    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
    gets
    -0.09
     Urteil
    -0.08
     акции
    -0.08
    sale
    -0.08
    dos
    -0.07
     Zwecke
    -0.07
    mdash
    -0.07
    meldung
    -0.07
    whether
    -0.07
    Millis
    -0.07
    POSITIVE LOGITS
    程度
    0.08
     naš
    0.08
     acute
    0.08
    crow
    0.08
    同行
    0.07
     درد
    0.07
     وزن
    0.07
    �
    0.07
     documental
    0.07
    rd
    0.07
    Activations Density 0.009%

    No Known Activations