© 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. 95386
    Prev
    Next
    INDEX
    Explanations

    cover

    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
     particip
    -0.08
     POV
    -0.08
    overe
    -0.07
    inf
    -0.07
     pointer
    -0.07
     pu
    -0.07
    _pointer
    -0.07
    inu
    -0.07
     Pointer
    -0.07
     Knowing
    -0.07
    POSITIVE LOGITS
     
    0.08
    ghanistan
    0.08
     eingesch
    0.08
     simmer
    0.08
    :\/\/
    0.08
     descending
    0.08
     burners
    0.08
    routine
    0.07
     sicrhau
    0.07
    =True
    0.07
    Activations Density 0.003%

    No Known Activations