© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 5385
    Prev
    Next
    INDEX
    Explanations

    say "inity" or "inely"

    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
    ienz
    -0.09
    ированных
    -0.09
    ing
    -0.09
    ированы
    -0.09
    erio
    -0.09
    િંગ
    -0.09
    azu
    -0.08
    arefa
    -0.08
     Conte
    -0.08
    enteri
    -0.08
    POSITIVE LOGITS
    inely
    0.12
    inity
    0.10
     pum
    0.09
     lwm
    0.08
     bene
    0.08
    .fml
    0.08
    ుత్వ
    0.08
    ILITY
    0.08
     RPG
    0.07
    us
    0.07
    Activations Density 0.001%

    No Known Activations