© 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. 97492
    Prev
    Next
    INDEX
    Explanations

    一

    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
     lighten
    -0.08
     bestens
    -0.07
     Paths
    -0.07
     bleach
    -0.07
     municipio
    -0.07
     നന്ദ
    -0.07
    ivez
    -0.07
     allons
    -0.07
     veuillez
    -0.07
    axed
    -0.07
    POSITIVE LOGITS
    流
    0.09
    ava
    0.08
     biomechanics
    0.08
     neurological
    0.08
     mechanical
    0.08
     নিউ
    0.08
     atua
    0.08
     Mensen
    0.08
     mechanically
    0.07
    kj
    0.07
    Activations Density 0.000%

    No Known Activations