© 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. 110859
    Prev
    Next
    INDEX
    Explanations

    skill

    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
    形
    -0.08
     результ
    -0.08
     downstream
    -0.08
    .sdk
    -0.08
     hinsichtlich
    -0.08
     mø
    -0.07
     kreative
    -0.07
    .output
    -0.07
     solusi
    -0.07
     آنے
    -0.07
    POSITIVE LOGITS
     proficiency
    0.10
     competencies
    0.10
    技能
    0.09
    skills
    0.09
     conocimientos
    0.09
     Kenntnisse
    0.09
     compétences
    0.09
     mastery
    0.09
     skills
    0.09
     ಪರಿಣ
    0.08
    Activations Density 0.005%

    No Known Activations