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. 44111
    Prev
    Next
    INDEX
    Explanations

    coal

    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
     Ell
    -0.09
     affine
    -0.08
    Affine
    -0.08
    יור
    -0.08
     Grass
    -0.08
     bless
    -0.08
     عام
    -0.07
     aff
    -0.07
     Meh
    -0.07
    ionale
    -0.07
    POSITIVE LOGITS
    -fired
    0.09
     drives
    0.09
     combustion
    0.08
    -burning
    0.08
    设施
    0.08
     Manchester
    0.08
     preta
    0.08
     Stove
    0.08
    houses
    0.08
     mines
    0.08
    Activations Density 0.004%

    No Known Activations