© 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. 96915
    Prev
    Next
    INDEX
    Explanations

    1

    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
    кті
    -0.09
    ophone
    -0.09
    əl
    -0.08
    énées
    -0.08
    ässig
    -0.08
    ком
    -0.08
    èn
    -0.08
    стары
    -0.08
    اں
    -0.08
    .Mutable
    -0.08
    POSITIVE LOGITS
     cuchar
    0.11
     on
    0.10
     taza
    0.10
     tassa
    0.09
     rama
    0.09
     colher
    0.09
     got
    0.09
     cd
    0.08
     litro
    0.08
     chor
    0.08
    Activations Density 0.001%

    No Known Activations