© 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. 6215
    Prev
    Next
    INDEX
    Explanations

    say the number 26

    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
     conjunct
    -0.08
    zier
    -0.08
    utsu
    -0.08
    @Id
    -0.08
    isis
    -0.08
     doctr
    -0.08
    @Module
    -0.07
     Sve
    -0.07
    _NULL
    -0.07
    Sve
    -0.07
    POSITIVE LOGITS
     tm
    0.07
     Audio
    0.07
    _tm
    0.07
    .tv
    0.07
     сети
    0.07
     apostar
    0.07
     pipes
    0.07
    tm
    0.07
     épocas
    0.06
     भारी
    0.06
    Activations Density 0.003%

    No Known Activations