© 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. 18939
    Prev
    Next
    INDEX
    Explanations

    ks

    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
    ’écran
    -0.10
     kosong
    -0.09
    basoke
    -0.09
    entañ
    -0.08
    Qué
    -0.08
    'écran
    -0.08
    lebn
    -0.08
     calme
    -0.08
     వంటి
    -0.08
    ecurity
    -0.08
    POSITIVE LOGITS
     נס
    0.08
     constituents
    0.07
     constituent
    0.07
     представители
    0.07
     lubricant
    0.07
     darte
    0.07
     eher
    0.07
     antaa
    0.07
     formatting
    0.06
    _cross
    0.06
    Activations Density 0.000%

    No Known Activations