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. 111718
    Prev
    Next
    INDEX
    Explanations

    full

    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
     facade
    -0.08
    孙
    -0.08
    _public
    -0.08
     Public
    -0.08
    public
    -0.08
     façade
    -0.08
    _PUBLIC
    -0.08
     immortal
    -0.07
    Trading
    -0.07
    -0.07
    POSITIVE LOGITS
     sensación
    0.10
     cravings
    0.10
     महसूस
    0.10
     ощущения
    0.09
     pare
    0.09
     feeling
    0.09
     Feeling
    0.09
    gefühl
    0.09
     sensação
    0.09
    -lasting
    0.09
    Activations Density 0.005%

    No Known Activations