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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 97353
    Prev
    Next
    INDEX
    Explanations

    nhu

    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
     بحق
    -0.08
     mixes
    -0.08
     �
    -0.08
    рыв
    -0.08
     mix
    -0.08
     mezcl
    -0.08
    orgon
    -0.08
     വള
    -0.08
    يمين
    -0.08
    ärke
    -0.07
    POSITIVE LOGITS
    入
    0.09
    ujen
    0.09
     nka
    0.09
     utilizadas
    0.08
    ులు
    0.08
     nri
    0.07
    Util
    0.07
     nso
    0.07
    _util
    0.07
     utilisées
    0.07
    Activations Density 0.001%

    No Known Activations