© 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. 45224
    Prev
    Next
    INDEX
    Explanations

    sponge

    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
     threaten
    -0.08
     riesgos
    -0.08
     threatened
    -0.08
     বিধ
    -0.08
     застав
    -0.08
     pund
    -0.08
     বিব
    -0.08
    ীন
    -0.08
    威
    -0.08
     minorities
    -0.07
    POSITIVE LOGITS
     absor
    0.09
     foam
    0.09
     porous
    0.09
     recept
    0.09
     sponge
    0.08
     naturally
    0.08
    �
    0.08
     drainage
    0.08
     vein
    0.08
     cushioning
    0.08
    Activations Density 0.006%

    No Known Activations