© 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. 63068
    Prev
    Next
    INDEX
    Explanations

    salty

    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
     जिसके
    -0.09
    روح
    -0.08
    aphezu
    -0.08
     Room
    -0.08
     Edith
    -0.08
     вид
    -0.08
     mindfulness
    -0.08
    志
    -0.08
     Flex
    -0.08
    दी
    -0.08
    POSITIVE LOGITS
     salty
    0.09
    aturated
    0.08
     feta
    0.07
    Analyze
    0.07
    bbox
    0.07
    Automatically
    0.07
    	cfg
    0.07
     institutions
    0.07
     caracter
    0.07
    zige
    0.07
    Activations Density 0.008%

    No Known Activations