© 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. 6020
    Prev
    Next
    INDEX
    Explanations

    entr

    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
    VALU
    -0.09
     Novomatic
    -0.09
    ๒
    -0.09
     մեջ
    -0.08
    λίου
    -0.08
     Ceará
    -0.08
    μβρίου
    -0.08
    τοποι
    -0.08
     author's
    -0.08
    ့
    -0.08
    POSITIVE LOGITS
    ées
    0.10
    antes
    0.10
    ée
    0.10
    ances
    0.09
    Fees
    0.09
    ants
    0.09
     fees
    0.09
    ando
    0.09
    анты
    0.08
     exam
    0.08
    Activations Density 0.010%

    No Known Activations