Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 18983
    Prev
    Next
    INDEX
    Explanations

    Solving equations

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prezent
    -0.08
     وتق
    -0.08
     Pró
    -0.08
    jou
    -0.08
     calcul
    -0.08
     purifier
    -0.08
     récent
    -0.08
     Intl
    -0.08
     recycl
    -0.07
     refroid
    -0.07
    POSITIVE LOGITS
     equations
    0.11
     clues
    0.09
     unpack
    0.09
     mismatch
    0.09
     impose
    0.08
     solving
    0.08
     evident
    0.08
     constraints
    0.08
     firstly
    0.08
     solve
    0.08
    Activations Density 0.041%

    No Known Activations