© 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. 7-RESID-POST-AA
    11. 1271
    Prev
    Next
    INDEX
    Explanations

    Girl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pore
    -0.09
     bow
    -0.08
     bedtime
    -0.08
     potenti
    -0.08
     beneath
    -0.07
     ru
    -0.07
     nond
    -0.07
     лес
    -0.07
     beispielsweise
    -0.07
     bete
    -0.07
    POSITIVE LOGITS
    _AG
    0.08
     Tib
    0.07
     AU
    0.07
     Joe
    0.07
    _COUNTER
    0.07
    们
    0.07
    vf
    0.07
    Counter
    0.07
    urf
    0.07
     Myrtle
    0.07
    Activations Density 0.029%

    No Known Activations