© 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. 48720
    Prev
    Next
    INDEX
    Explanations

    Computer hardware/GPUs

    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
    র্ষ
    -0.10
     တွ
    -0.09
    ~-
    -0.09
     nep
    -0.08
     obrigatório
    -0.08
     Cand
    -0.08
    …..
    -0.08
     �
    -0.08
    orsunuz
    -0.08
     숫
    -0.08
    POSITIVE LOGITS
    Studio
    0.08
    lesson
    0.08
    =config
    0.08
    PLUS
    0.08
    Ubuntu
    0.08
    LB
    0.08
    FX
    0.08
    ubuntu
    0.08
    Linux
    0.08
    Dropbox
    0.08
    Activations Density 0.004%

    No Known Activations