© 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. 47259
    Prev
    Next
    INDEX
    Explanations

    Cialdini's persuasion psychology

    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
    τερ
    -0.08
    tach
    -0.08
    βα
    -0.08
     біл
    -0.08
     granddaughter
    -0.08
    　　　　　　　　
    -0.08
     sewage
    -0.08
    <Map
    -0.07
    <any
    -0.07
     διε
    -0.07
    POSITIVE LOGITS
    魅
    0.09
     mastery
    0.08
     cues
    0.07
     orn
    0.07
    itations
    0.07
    .htm
    0.07
    -Mark
    0.07
     auc
    0.07
    ifr
    0.07
     fascinating
    0.07
    Activations Density 0.004%

    No Known Activations