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. 49114
    Prev
    Next
    INDEX
    Explanations

    )(

    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
     unrealistic
    -0.09
     optimistic
    -0.09
     acceleration
    -0.08
     jov
    -0.08
     grateful
    -0.08
     accelerating
    -0.08
     ratios
    -0.08
    -स
    -0.08
     textures
    -0.08
     accelerate
    -0.08
    POSITIVE LOGITS
    ximity
    0.08
     Opinion
    0.08
    tv
    0.07
    venue
    0.07
     değerlend
    0.07
     Copyright
    0.07
     celebrity
    0.07
    inding
    0.07
     dra
    0.07
    _cd
    0.07
    Activations Density 0.031%

    No Known Activations