© 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. 108740
    Prev
    Next
    INDEX
    Explanations

    -

    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
     сопровож
    -0.09
     каких
    -0.08
     сопров
    -0.08
     отече
    -0.08
     مطرح
    -0.08
    -0.08
     ف
    -0.08
     акс
    -0.07
     ulo
    -0.07
     остальных
    -0.07
    POSITIVE LOGITS
     jez
    0.08
     arranged
    0.08
    owan
    0.07
    습
    0.07
    라이
    0.07
    _BL
    0.07
     destiny
    0.07
    0.07
     arrangement
    0.07
    安排
    0.07
    Activations Density 0.001%
    No Known Activations