Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55895
    Prev
    Next
    INDEX
    Explanations

    PsychoPy library

    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
     intimately
    -0.09
     motto
    -0.09
    @yahoo
    -0.09
     quaint
    -0.09
     gallon
    -0.09
     miraculous
    -0.09
     lantern
    -0.09
    Bill
    -0.09
    _bill
    -0.09
    �
    -0.08
    POSITIVE LOGITS
     EEG
    0.10
     QA
    0.10
     stimuli
    0.09
     randomized
    0.09
     habitu
    0.09
     Shuffle
    0.09
     electrode
    0.08
     participants
    0.08
     the
    0.08
     Forschungs
    0.08
    Activations Density 0.005%

    No Known Activations