© 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. 47966
    Prev
    Next
    INDEX
    Explanations

    defamation

    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
    /env
    -0.08
     seating
    -0.08
     Assist
    -0.08
     Seating
    -0.08
     snacks
    -0.08
     convirtió
    -0.08
     metallic
    -0.08
     asistencia
    -0.07
     erfolgreich
    -0.07
     assist
    -0.07
    POSITIVE LOGITS
     allegations
    0.12
     defamatory
    0.10
     ആരോപ
    0.10
     accusations
    0.10
     lawsuit
    0.10
     accusation
    0.10
     attribution
    0.10
     allegation
    0.09
    涉嫌
    0.09
     alleged
    0.09
    Activations Density 0.009%

    No Known Activations