© 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. 19-RESID-POST-AA
    11. 103110
    Prev
    Next
    INDEX
    Explanations

    fractions

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     immersion
    -0.09
    лия
    -0.09
     immersive
    -0.09
    lernen
    -0.08
    ’après
    -0.08
    ранс
    -0.08
    ření
    -0.08
    eyond
    -0.08
     করার
    -0.08
     prostřed
    -0.08
    POSITIVE LOGITS
     numerator
    0.41
     denominator
    0.23
    umerator
    0.21
    numer
    0.17
     Numer
    0.16
    )/(
    0.16
    ominator
    0.16
    Numer
    0.16
    ))/(
    0.13
     denom
    0.12
    Activations Density 0.153%

    No Known Activations