© 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. 11-RESID-POST-AA
    11. 24698
    Prev
    Next
    INDEX
    Explanations

    hand preference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     concepto
    -0.09
     conceito
    -0.08
     conducted
    -0.07
     delar
    -0.07
     unmittelbar
    -0.07
     concept
    -0.07
     inmediato
    -0.07
    .Server
    -0.07
    =\"#
    -0.07
     thanh
    -0.07
    POSITIVE LOGITS
    Preference
    0.11
     Preference
    0.10
     predominant
    0.09
    -handed
    0.09
    Nowadays
    0.09
     preference
    0.09
     preferência
    0.09
    Preferences
    0.08
     halves
    0.08
     предпочт
    0.08
    Activations Density 0.007%

    No Known Activations