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. 97076
    Prev
    Next
    INDEX
    Explanations

    say "cash"

    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
     Ursula
    -0.10
     autism
    -0.10
     winger
    -0.09
     Triangle
    -0.09
     Srb
    -0.09
     Vog
    -0.09
     Trondheim
    -0.09
     vowel
    -0.09
     mites
    -0.09
     Autism
    -0.09
    POSITIVE LOGITS
     cash
    0.59
    现金
    0.54
    Cash
    0.53
    _cash
    0.53
     Cash
    0.53
    cash
    0.51
    .cash
    0.47
     CASH
    0.43
     নগ
    0.35
     नक
    0.34
    Activations Density 0.082%

    No Known Activations