© 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. 6162
    Prev
    Next
    INDEX
    Explanations

    hands and muscles

    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
    akana
    -0.08
    etje
    -0.08
     καθη
    -0.08
     fiddle
    -0.08
     pagka
    -0.08
    Skype
    -0.08
    ddy
    -0.08
     Constitutional
    -0.07
    orset
    -0.07
    kọ
    -0.07
    POSITIVE LOGITS
     plan
    0.13
     muscle
    0.12
     hand
    0.12
     Hand
    0.11
    Hand
    0.11
     développé
    0.10
     Muscle
    0.10
    Plan
    0.10
     Händen
    0.10
     Plan
    0.10
    Activations Density 0.006%

    No Known Activations