© 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. 68097
    Prev
    Next
    INDEX
    Explanations

    ather

    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
     Gonzalez
    -0.08
    �
    -0.08
     mañana
    -0.07
     iphone
    -0.07
     سوء
    -0.07
    קים
    -0.07
    urtles
    -0.07
    amau
    -0.07
     suspe
    -0.07
     ডিজ
    -0.07
    POSITIVE LOGITS
    Affinity
    0.08
    lié
    0.08
    -Nov
    0.08
    lycer
    0.08
    Bo
    0.07
    ļa
    0.07
    AGER
    0.07
    uba
    0.07
    plates
    0.07
    ilin
    0.07
    Activations Density 0.001%

    No Known Activations