© 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. 97293
    Prev
    Next
    INDEX
    Explanations

    ide

    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
    aditional
    -0.08
    렸다
    -0.08
    리는
    -0.08
    -case
    -0.08
    soap
    -0.08
     physiology
    -0.08
    arding
    -0.08
    ıldığı
    -0.07
    imt
    -0.07
    렸
    -0.07
    POSITIVE LOGITS
     ideological
    0.11
    ological
    0.11
    ologues
    0.11
    als
    0.10
    ologue
    0.10
    ology
    0.09
    喊
    0.09
    ologique
    0.08
    ologies
    0.08
     ideology
    0.08
    Activations Density 0.002%

    No Known Activations