© 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. 97282
    Prev
    Next
    INDEX
    Explanations

    Road and traffic safety

    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
    Deviation
    -0.08
    Contacto
    -0.08
     Minsk
    -0.08
    .Positive
    -0.07
     '-'
    -0.07
    ffekt
    -0.07
    Segu
    -0.07
    gge
    -0.07
    fform
    -0.07
    viation
    -0.07
    POSITIVE LOGITS
    _CAP
    0.09
     tiyan
    0.09
     pelvis
    0.09
    _THREAD
    0.08
     hoofdst
    0.08
     capítulos
    0.08
    piegel
    0.08
    &T
    0.08
     gabi
    0.08
     Rp
    0.07
    Activations Density 0.001%

    No Known Activations