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. 98077
    Prev
    Next
    INDEX
    Explanations

    say ending with 'ir' or 'ible'

    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
    izzare
    -0.09
    фикации
    -0.09
    ային
    -0.09
    arity
    -0.09
    άζεται
    -0.09
    ณะ
    -0.09
    arani
    -0.09
    arczy
    -0.09
    ายใน
    -0.08
    izzazione
    -0.08
    POSITIVE LOGITS
    ido
    0.28
    idos
    0.24
    ida
    0.24
    iremos
    0.24
    ir
    0.23
    idas
    0.22
    idamente
    0.22
    irse
    0.22
    iendo
    0.21
    idores
    0.20
    Activations Density 0.025%

    No Known Activations