© 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. 23-RESID-POST-AA
    11. 50743
    Prev
    Next
    INDEX
    Explanations

    innocence

    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
    udier
    -0.08
    अ
    -0.07
     dheer
    -0.07
    ाकर
    -0.07
     allocation
    -0.07
     andet
    -0.07
     Inde
    -0.07
     hỗ
    -0.07
     associative
    -0.07
    総
    -0.07
    POSITIVE LOGITS
    uous
    0.20
     innoc
    0.15
    uité
    0.14
     innocent
    0.12
    ence
    0.12
    ulated
    0.12
    ulation
    0.12
    ulate
    0.12
     innocence
    0.12
    ulations
    0.11
    Activations Density 0.004%

    No Known Activations