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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19375
    Prev
    Next
    INDEX
    Explanations

    Online meeting controls

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TAC
    -0.09
    autoload
    -0.09
     voyages
    -0.08
     SIST
    -0.08
     prazo
    -0.08
     giorno
    -0.08
    .Calendar
    -0.08
     дней
    -0.08
    _SITE
    -0.08
    JSONException
    -0.08
    POSITIVE LOGITS
     muted
    0.12
    Moderator
    0.12
     microphones
    0.11
     breakout
    0.11
     moderators
    0.11
    人数
    0.11
    聊天室
    0.11
     audio
    0.10
    桌
    0.10
     mute
    0.10
    Activations Density 0.010%

    No Known Activations