© 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. 97340
    Prev
    Next
    INDEX
    Explanations

    Quantities and calculations

    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
    comme
    -0.09
    ்ச்சி
    -0.08
    minen
    -0.08
    іні
    -0.08
    Java
    -0.08
    -none
    -0.08
    -one
    -0.08
    like
    -0.08
    cano
    -0.08
     mình
    -0.07
    POSITIVE LOGITS
    ాత
    0.14
     æt
    0.13
     at
    0.13
     أت
    0.13
    াত
    0.13
     atleta
    0.12
    ಾತ
    0.12
    ात
    0.12
    ാത
    0.12
    	at
    0.12
    Activations Density 0.047%

    No Known Activations