© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 97455
    Prev
    Next
    INDEX
    Explanations

    Code snippets and documentation

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    アイ
    -0.08
    zej
    -0.07
    販売
    -0.07
    shalling
    -0.07
    発送
    -0.07
    ijek
    -0.07
    865
    -0.07
    j
    -0.07
     ibintu
    -0.07
     finishing
    -0.07
    POSITIVE LOGITS
    َع
    0.07
     weers
    0.07
    'ac
    0.07
    ly
    0.07
     mastered
    0.07
    ’ac
    0.07
     acet
    0.07
     Ac
    0.07
    ac
    0.07
     ac
    0.07
    Activations Density 0.001%

    No Known Activations