© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18339
    Prev
    Next
    INDEX
    Explanations

    capac

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     focus
    -0.08
     Stream
    -0.07
    als
    -0.07
     DIY
    -0.07
    יגע
    -0.07
     bold
    -0.07
     stride
    -0.07
    יז
    -0.07
    =============
    -0.07
     letters
    -0.07
    POSITIVE LOGITS
    capac
    0.10
    itating
    0.10
     capacitor
    0.10
    itated
    0.10
     capacit
    0.09
    iteit
    0.09
    upaten
    0.09
    entai
    0.09
    feest
    0.09
    cpf
    0.08
    Activations Density 0.020%

    No Known Activations