© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 71398
    Prev
    Next
    INDEX
    Explanations

    phot

    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
    	Write
    -0.08
     fasting
    -0.08
    ，共
    -0.08
    local
    -0.08
     dersom
    -0.08
     lokalen
    -0.08
     dirigente
    -0.07
     estrogen
    -0.07
     �
    -0.07
     menstrual
    -0.07
    POSITIVE LOGITS
     realism
    0.10
     realistic
    0.09
     reality
    0.08
     simulation
    0.08
     footage
    0.08
     portray
    0.08
     Reality
    0.08
     plein
    0.07
     현실
    0.07
    Reality
    0.07
    Activations Density 0.006%

    No Known Activations