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. 60472
    Prev
    Next
    INDEX
    Explanations

    website text

    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
    BDD
    -0.08
     perkara
    -0.08
     referred
    -0.08
    xxxxx
    -0.08
     contr
    -0.08
    heap
    -0.08
    _WINDOW
    -0.08
     bauen
    -0.08
    	task
    -0.07
    IMUM
    -0.07
    POSITIVE LOGITS
     μεγάλη
    0.08
     Transpar
    0.07
     Klick
    0.07
     Transparency
    0.07
     linh
    0.07
     Click
    0.07
     unob
    0.07
     Payment
    0.07
     Exit
    0.07
     Responsive
    0.07
    Activations Density 0.447%

    No Known Activations