Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130783
    Prev
    Next
    INDEX
    Explanations

    pituitary gland

    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
     Profes
    -0.09
    "La
    -0.09
     odm
    -0.09
     Urdu
    -0.08
     uintptr
    -0.08
     herk
    -0.08
     redux
    -0.08
     abst
    -0.08
     mowing
    -0.08
     Esperanto
    -0.08
    POSITIVE LOGITS
     pit
    0.17
     hypoth
    0.15
     anterior
    0.14
    Pit
    0.14
     Pit
    0.14
    pit
    0.13
     pancreatic
    0.12
     PIT
    0.10
    Anterior
    0.10
     pine
    0.10
    Activations Density 0.006%

    No Known Activations