© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18657
    Prev
    Next
    INDEX
    Explanations

    on

    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
    త్న
    -0.08
    σεων
    -0.08
     también
    -0.08
    _ROLE
    -0.08
     ogé
    -0.08
     बताएका
    -0.07
     पनि
    -0.07
    ებულია
    -0.07
    also
    -0.07
    ření
    -0.07
    POSITIVE LOGITS
     either
    0.23
    either
    0.20
    Either
    0.19
     sides
    0.18
     entweder
    0.18
     Either
    0.18
     opposite
    0.18
     begge
    0.17
     lados
    0.17
     ambos
    0.16
    Activations Density 0.039%

    No Known Activations