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. 26672
    Prev
    Next
    INDEX
    Explanations

    Clarification requests

    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
    -bordered
    -0.08
    lymp
    -0.08
    424
    -0.08
    vilupp
    -0.07
    ্রম
    -0.07
     Nex
    -0.07
    030
    -0.07
    rista
    -0.07
     kissing
    -0.07
    hen
    -0.07
    POSITIVE LOGITS
     gedachte
    0.11
     mind
    0.11
    想到
    0.10
    念
    0.10
     મન
    0.10
     mindset
    0.10
     gedachten
    0.10
     Vorstellungen
    0.10
     meinst
    0.10
     मन
    0.10
    Activations Density 0.015%

    No Known Activations