© 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. 97385
    Prev
    Next
    INDEX
    Explanations

    say "present"

    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
    或者
    -0.08
    /orders
    -0.08
    几个
    -0.08
    或
    -0.08
     nekoliko
    -0.08
    =http
    -0.08
     kekere
    -0.08
     или
    -0.08
    olith
    -0.08
     unteren
    -0.08
    POSITIVE LOGITS
     present
    0.28
    Present
    0.27
    present
    0.27
    _present
    0.27
     Present
    0.26
     presente
    0.25
     présent
    0.24
    -present
    0.24
    .present
    0.22
     presenti
    0.22
    Activations Density 0.027%

    No Known Activations