© 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. 48132
    Prev
    Next
    INDEX
    Explanations

    exists

    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
     considerados
    -0.11
     considered
    -0.11
     consideradas
    -0.10
     assumed
    -0.10
     החדש
    -0.09
    ինը
    -0.09
     gathered
    -0.09
     предполага
    -0.09
    .each
    -0.09
     Given
    -0.09
    POSITIVE LOGITS
     exists
    0.13
     એવો
    0.12
     solution
    0.12
     choice
    0.12
     olyan
    0.12
     suitable
    0.12
     એવી
    0.11
    Exists
    0.11
    _exists
    0.11
     decomposition
    0.11
    Activations Density 0.107%

    No Known Activations