© 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. 3-RESID-POST-AA
    11. 12774
    Prev
    Next
    INDEX
    Explanations

    fully

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setter
    -0.08
    Reserv
    -0.07
     bene
    -0.07
    策
    -0.07
    措
    -0.07
     לט
    -0.07
     bele
    -0.07
    ेख
    -0.07
    setter
    -0.07
    arah
    -0.07
    POSITIVE LOGITS
     stages
    0.08
    nj
    0.08
    油
    0.08
    EY
    0.08
    	stage
    0.08
     uprising
    0.08
     مرحلة
    0.08
    -stage
    0.07
     SIT
    0.07
     выполнить
    0.07
    Activations Density 0.010%

    No Known Activations