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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 26727
    Prev
    Next
    INDEX
    Explanations

    surveys and public opinion

    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
    gred
    -0.09
     accrued
    -0.08
    ockets
    -0.08
     CONSTANT
    -0.07
    Trail
    -0.07
     peeled
    -0.07
     massif
    -0.07
    betal
    -0.07
    glib
    -0.07
    네
    -0.07
    POSITIVE LOGITS
     willingness
    0.09
     préf
    0.09
     prefere
    0.08
     liking
    0.08
     предпоч
    0.08
     respondents
    0.08
     questionnaire
    0.08
     desire
    0.08
     voorkeur
    0.08
     preference
    0.08
    Activations Density 0.052%

    No Known Activations