© 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. 2636
    Prev
    Next
    INDEX
    Explanations

    story

    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
     Spar
    -0.09
     Mall
    -0.08
     transpose
    -0.07
     сув
    -0.07
     ní
    -0.07
    ठ
    -0.07
     Sussex
    -0.07
    Mit
    -0.07
     intrac
    -0.07
    Oc
    -0.07
    POSITIVE LOGITS
     slim
    0.08
    _basic
    0.08
    पूर्ण
    0.08
    (In
    0.07
     hin
    0.07
    _pat
    0.07
     kitten
    0.07
    362
    0.07
     Carm
    0.07
     Cach
    0.07
    Activations Density 0.033%

    No Known Activations