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. 11-RESID-POST-AA
    6. 120366
    Prev
    Next
    INDEX
    Explanations

    sharp

    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
     indeb
    -0.08
    Tencent
    -0.08
     zufolge
    -0.08
     चली
    -0.08
    疫情
    -0.08
    _Login
    -0.08
     Girls
    -0.08
    .Te
    -0.08
     faveur
    -0.08
    __(↵
    -0.08
    POSITIVE LOGITS
     capable
    0.09
    -l
    0.09
     enough
    0.09
    Enough
    0.08
    ailable
    0.07
    Bone
    0.07
    ust
    0.07
     everywhere
    0.07
     lin
    0.07
    erb
    0.07
    Activations Density 0.004%

    No Known Activations